CN109668732A - The method for diagnosing faults of rolling bearing based on circulation joint entropy - Google Patents
The method for diagnosing faults of rolling bearing based on circulation joint entropy Download PDFInfo
- Publication number
- CN109668732A CN109668732A CN201811510327.8A CN201811510327A CN109668732A CN 109668732 A CN109668732 A CN 109668732A CN 201811510327 A CN201811510327 A CN 201811510327A CN 109668732 A CN109668732 A CN 109668732A
- Authority
- CN
- China
- Prior art keywords
- bearing
- fault
- data
- joint entropy
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The present invention provides a kind of method for diagnosing faults of rolling bearing based on circulation joint entropy.This method comprises: acquisition rolling bearing is in the bearing data under different faults state respectively, the fault characteristic frequency of every kind of failure is calculated；Windowing process is carried out to bearing data, bearing data are divided into multiple data blocks, gaussian kernel function is chosen as the kernel function for recycling joint entropy, calculates Fourier transformation result of the mean value in the domain f of the averaging loop joint entropy of each data block and the Fourier transformation of averaging loop joint entropy；Projection according to Fourier transformation result in the domain alpha obtains the spectrum distribution of fault-signal as a result, judging according to the fault characteristic frequency of the bearing data under the spectrum distribution result and every kind of malfunction of fault-signal the fault type of bearing.Method of the invention can preferably be handled under non-Gaussian noise environment, especially the faulty bearings signal under impact noise disturbed condition, can better meet the requirement of engineering practice.
Description
Technical field
The present invention relates to bearing failure diagnosis technical field more particularly to a kind of rolling bearings based on circulation joint entropy
Method for diagnosing faults.
Background technique
Rolling bearing using very extensive, rolls in mechanical engineering field under high-intensitive and highdensity operating condition
Dynamic bearing has very high failure rate.Therefore, it is monitored by state of the method for diagnosing faults to rolling bearing, in real time more
Change faulty bearings is just particularly important with the normal operation for guaranteeing mechanical equipment.
When parts of bearings surface is broken down, shock can be generated with other component surface during rotation, thus
Generate a series of impact signals modulated.This fault message is distributed in some frequency range of signal, if can pass through signal
Processing method obtains the higher failure band information of signal-to-noise ratio, and failure can be detected.
Therefore, a large amount of concerns of domestic and foreign scholars have been obtained based on the preferred method for diagnosing faults of frequency band.But it is actually grinding
Study carefully middle discovery, the bearing vibration signal in engineering practice is usually associated with a large amount of non-Gaussian noise, frequency band optimization algorithm it is steady
The qualitative interference that will receive this kind of non-Gaussian noise causes fault diagnosis result inaccurate.
Summary of the invention
The embodiment provides it is a kind of based on circulation joint entropy rolling bearing method for diagnosing faults, with gram
Take problem of the prior art.
To achieve the goals above, this invention takes following technical solutions:
A kind of method for diagnosing faults of the rolling bearing based on circulation joint entropy characterized by comprising
Acquisition rolling bearing is in the bearing data under different faults state respectively, and the malfunction includes rolling element
Failure, inner ring failure and outer ring failure calculate the fault characteristic frequency of the bearing data under every kind of malfunction；
Windowing process is carried out to the bearing data, bearing data are divided into multiple data blocks, choose gaussian kernel function
As the kernel function of circulation joint entropy, the averaging loop joint entropy of each data block is calculated, averaging loop joint entropy is calculated
Fourier transformation mean value the domain f Fourier transformation result；
Projection according to the Fourier transformation result in the domain alpha obtain the spectrum distribution of fault-signal as a result, according to
The fault characteristic frequency of the spectrum distribution result of the fault-signal and the bearing data under every kind of malfunction is to bearing
Fault type judged.
Further, the fault characteristic frequency for calculating the bearing data under every kind of malfunction, comprising:
The calculation formula of the characteristic frequency of outer ring failure is as follows:
The calculation formula of the characteristic frequency of inner ring failure is as follows:
The calculation formula of the characteristic frequency of rolling element failure is as follows:
frIndicating the speed of shaft, n indicates the rolling element number of bearing,Indicate that load sagittal plane angle, d indicate
The diameter of rolling element, D indicate bearing bore diameter.
Further, described that windowing process is carried out to the bearing data, bearing data are divided into multiple data
Block chooses kernel function of the gaussian kernel function as circulation joint entropy, calculates the averaging loop joint entropy of each data block, wraps
It includes:
Bearing data x [n] under different faults state is in the rolling bearing of acquisition and carries out adding window, by bearing data x
[n] is divided into L data block, and each data block has N number of sample point；
Kernel function of the gaussian kernel function as circulation joint entropy is chosen, each data block is calculated according to Silverman criterion
Circulation joint entropy core width cs:
X, y indicate the random signal of two equal lengths, and κ (x-y) indicates gaussian kernel function table；
σ indicates the core width of circulation joint entropy；
σ=0.9A*N-1/5 (5)
A indicates the interquartile range of sample standard deviation and sample divided by 1.34 minimum value, and N indicates sample points；
Calculate the averaging loop joint entropy M of each data blockl, l=0,1,2 ..., L-1；
τnIndicate the translation interval between data block；xl[n] indicates the former data of data block, xl[n+τn] indicate former data
Translate τnNew data afterwards, κ (xl[n],xl[n+τn]) indicate to calculate the joint entropy for translating former and later two data blocks.
Further, Fourier of the mean value of the Fourier transformation for calculating averaging loop joint entropy in the domain f becomes
Change result, comprising:
The centralization for calculating time-domain signal based on L data block recycles joint entropy, and calculates centralization circulation joint entropy and exist
The Fourier transformation result in the domain alphaThe domain alpha refers to modulating frequency, i.e. domain where the failure-frequency of bearing；
α [n] indicates cycle frequency, G (xl[n],xl[n+τn]) indicate centralization before translation front and back two data blocks circulation
Joint entropy, MlIndicate averaging loop joint entropy, [G (xl[n],xl[n+τn])-MlIndicate that centralization recycles joint entropy；
Calculate the averaging loop joint entropy M of L data blocklFourier transformation mean value
Calculate mean valueFourier transformation result T in the domain fα；
The domain f above refers to carrier frequency, i.e. domain where resonant frequency.
Further, the projection according to the Fourier transformation result in the domain alpha obtains the frequency of fault-signal
Spectral structure is as a result, according to the event of the bearing data under the spectrum distribution result of the fault-signal and every kind of malfunction
Barrier characteristic frequency judges the fault type of bearing, comprising:
The characteristic frequency of rolling element failure is set as 52Hz, the characteristic frequency of inner ring failure is 162Hz, outer ring failure
Characteristic frequency is 120Hz；
Projection according to the Fourier transformation result in the domain alpha obtains the spectrum distribution of fault-signal as a result, when event
Hinder the threshold value that the difference between the frequency of signal and the characteristic frequency of rolling element failure is less than setting, then judges the failure of bearing
Type is rolling element failure；When the difference between the frequency of fault-signal and the characteristic frequency of inner ring failure is less than the threshold of setting
Value, then judge the fault type of bearing for inner ring failure；When between the frequency of fault-signal and the characteristic frequency of outer ring failure
Difference is less than the threshold value of setting, then judges the fault type of bearing for outer ring failure.
As can be seen from the technical scheme provided by the above-mentioned embodiment of the present invention, provided in an embodiment of the present invention to be based on following
The method for diagnosing faults of the rolling bearing of ring joint entropy is according to the steady Modeling Theory of bearing vibration signal cycle, using core
Data are mapped to Hilbert space from Euclidean space by the method for Function Mapping, can preferably be handled in non-gaussian
It, can be under conditions of signal of rolling bearing be interfered by impact noise, accurately to the failure classes of rolling bearing under noise circumstance
Type distinguishes, and can preferably meet the requirement of engineering practice.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will from the following description
Become obvious, or practice through the invention is recognized.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, making required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, right
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of rolling bearing intelligent failure diagnosis method based on circulation joint entropy provided in an embodiment of the present invention
Process flow diagram；
Fig. 2 is that a kind of local fault of faulty bearings provided in an embodiment of the present invention is as shown in Figure 1, wherein rolling element event
Hinder (a), inner ring failure (b) and outer ring failure (c)；
Fig. 3 is that a kind of transverse load bringing device by testing stand provided in an embodiment of the present invention is all to bearing application
The schematic diagram of the impact noise of phase property；
Fig. 4 is a kind of joint entropy spectrogram of bearing roller faulty bearings signal provided in an embodiment of the present invention, arrow table
Show the peak value of rolling element fault characteristic frequency；
Fig. 5 is a kind of joint entropy spectrogram of bearing inner race faulty bearings signal provided in an embodiment of the present invention, and arrow indicates
The peak value of inner ring fault characteristic frequency；
Fig. 6 is a kind of joint entropy spectrogram of bearing outer ring faulty bearings signal provided in an embodiment of the present invention, and arrow indicates
The peak value of outer ring fault characteristic frequency；
Fig. 7 is a kind of bearing roller failure letter analyzed based on spectrum kurtosis method provided in an embodiment of the present invention
Number analysis: figure (a) based on spectrum kurtosis signal decomposition；Scheming (b) is the envelope frequency spectrum obtained according to figure (a) preferred frequency band result
Figure；
Fig. 8 is a kind of bearing inner race fault-signal analyzed based on spectrum kurtosis method provided in an embodiment of the present invention
Analysis: signal decomposition of the figure (a) based on spectrum kurtosis；Scheming (b) is the envelope frequency spectrum figure obtained according to figure (a) preferred frequency band result；
Fig. 9 is a kind of bearing outer ring fault-signal analyzed based on spectrum kurtosis method provided in an embodiment of the present invention
Analysis: signal decomposition of the figure (a) based on spectrum kurtosis；Scheming (b) is the envelope frequency spectrum figure obtained according to figure (a) preferred frequency band result.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by
The embodiment being described with reference to the drawings is exemplary, and for explaining only the invention, and cannot be construed to limit of the invention
System.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or can also deposit
In intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.It is used herein to arrange
Diction "and/or" includes one or more associated any cells for listing item and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology
Term and scientific term) there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Also answer
It should be appreciated that those terms such as defined in the general dictionary should be understood that have in the context of the prior art
The consistent meaning of meaning will not be explained in an idealized or overly formal meaning and unless defined as here.
In order to facilitate understanding of embodiments of the present invention, it is done by taking several specific embodiments as an example into one below in conjunction with attached drawing
The explanation of step, and each embodiment does not constitute the restriction to the embodiment of the present invention.
Cyclo-stationary modeling method is used primarily for the analysis and processing of medical signals and signal of communication, introduces in recent years
To mechanical engineering field.Cyclo-stationary modeling method is greatly promoted rolling bearing fault Analysis on Mechanism and fault diagnosis effect
The promotion of fruit, this method is by extracting the cycle period ingredient in bearing vibration signal, by fault-signal from relatively by force
Ambient noise and other coupled vibrations interference signals among separate, realize to the fault diagnosis of bearing.
Joint entropy is the signal correlation metric index based on kernel function, and joint entropy is based on kernel method for initial data sky
Between be mapped to high-dimensional data space, the operation of signal similarity is carried out using the positive definite kernel function for meeting Mercer condition, it is related
Entropy can save the information of High Order Moment, to remain to stable correlation degree when signal is under non-Gaussian noise environment
Scale is existing.Therefore, joint entropy is studied in such as high-order feature extraction, impact noise estimation, especially Nonlinear harmonic oscillator etc.
In be widely used.
This embodiment offers a kind of process flows of rolling bearing intelligent failure diagnosis method based on circulation joint entropy
As shown in Figure 1, including following processing step:
Step 11 obtains experimental data: rolling bearing acquired respectively is in the bearing data under different faults state, it should
Bearing data include rolling element fault data, inner ring fault data and outer ring fault data, and the period is added in data acquired
Impact noise calculates the failure-frequency of bearing according to the technical parameter of bearing.
A kind of local fault of faulty bearings provided in an embodiment of the present invention is as shown in Figure 2, wherein rolling element failure
(a), inner ring failure (b) and outer ring failure (c), Fig. 3 are a kind of transverse load by testing stand provided in an embodiment of the present invention
Bringing device applies the schematic diagram of periodic impact noise to bearing.
The calculation formula of the characteristic frequency of outer ring failure is as follows:
The calculation formula of the characteristic frequency of inner ring failure is as follows:
The calculation formula of the characteristic frequency of rolling element failure is as follows:
frIndicating the speed of shaft, n indicates the rolling element number of bearing,Indicate that load sagittal plane angle, d indicate
The diameter of rolling element, D indicate bearing bore diameter；
Step 12 carries out adding window to the bearing data x [n] that step 11 obtains, and bearing data x [n] is divided into L number
According to block, each data block has N number of sample point；
Step 13 chooses kernel function of the gaussian kernel function as circulation joint entropy, according to Silverman criterion, calculates step
The core width cs of the circulation joint entropy of the rapid 12 each data blocks obtained；
Shown in calculation method such as formula (5)；
X, y indicate the random signal of two equal lengths, and κ (x-y) indicates gaussian kernel function table, the size control of core width cs
The window width of gaussian kernel function processed, core width is bigger, and window width is wider.
σ indicates the core width of circulation joint entropy；
σ=0.9A*N-1/5 (5)
A indicate the interquartile range of sample standard deviation and sample divided by 1.34 minimum value；
N indicates sample points.
Core width cs based on the circulation joint entropy that the L data block that step 12 obtains, step 13 obtain, calculate every number
According to the averaging loop joint entropy M of blockl, l=0,1,2 ..., L-1, calculation formula is such as shown in (6)；
τnIndicate the translation interval between data block；xl[n] indicates the former data of data block, xl[n+τn] indicate former data
Translate τnNew data afterwards, κ (xl[n],xl[n+τn]) indicate to calculate the joint entropy for translating former and later two data blocks.
What the core in κ (x-y) kernel function referred to is exactly core width, as shown in formula (4).
Step 14, the L data block obtained based on step 12, calculate the centralization circulation joint entropy of time-domain signal, and count
Centralization circulation joint entropy is calculated in the Fourier transformation result in the domain alphaThe domain alpha refers to modulating frequency, the i.e. event of bearing
Hinder the domain where frequency；
α [n] indicates cycle frequency, G (xl[n],xl[n+τn]) indicate centralization before translation front and back two data blocks circulation
Joint entropy, MlIndicate averaging loop joint entropy.
The expression formula that centralization recycles joint entropy is [G (xl[n],xl[n+τn])-Ml, calculate the mesh of centralization joint entropy
Realization circulation joint entropy zero-mean.
Step 15, the averaging loop joint entropy M for calculating L data blocklFourier transformation mean value
Calculate mean valueFourier transformation result T in the domain fα；
The domain f above refers to carrier frequency, i.e. domain where resonant frequency；
Step 16 extracts Fourier transformation resultProjection in the domain alpha obtains the spectrum distribution knot of fault-signal
Fruit, fault type of the fault characteristic frequency obtained according to the spectrum distribution result and step 11 of above-mentioned fault-signal to bearing
Judged.
The characteristic frequency of the rolling element failure obtained by theoretical calculation is 52Hz, and the characteristic frequency of inner ring failure is
162Hz, the characteristic frequency of outer ring failure are 120Hz, i.e. peak value difference in the corresponding frequency spectrum of three kinds of fault-signals where spectral peak
For 52Hz, 162Hz, 120Hz and its frequency multiplication.
Fault type can be judged according to the spectrum peak shown on frequency spectrum.According to the Fourier transformation result
Projection in the domain alpha obtains the spectrum distribution of fault-signal as a result, when the frequency of fault-signal and the feature of rolling element failure
Difference between frequency is less than the threshold value of setting, then judges the fault type of bearing for rolling element failure；When the frequency of fault-signal
Difference between rate and the characteristic frequency of inner ring failure is less than the threshold value of setting, then judges the fault type of bearing for inner ring event
Barrier；When threshold value of the difference between the frequency of fault-signal and the characteristic frequency of outer ring failure less than setting, then bearing is judged
Fault type is outer ring failure.The threshold value of above-mentioned setting is set according to actual conditions, and can be numerical value 1-5 etc..
Fig. 4-Fig. 6 shows respectively rolling element failure, inner ring failure and the corresponding joint entropy frequency spectrum signal of outer ring failure
Figure, the cycle frequency value where the arrow of Cong Tuzhong can be seen that spectral peak can be corresponding with the theoretical value being calculated, from
And failure-frequency and its frequency multiplication under three kinds of malfunctions can accurately be identified by demonstrating method proposed by the invention,
Realize the fault type diagnosis of bearing.
For the superiority that the present invention is further explained, the result obtained by Classical Spectrum kurtosis analysis method and this hair
The analysis result that the comparison of bright method, rolling element failure, inner ring failure and outer ring fault-signal obtain as shown in figs. 7 to 9, can be with
Find out the interference due to impact noise, composing the inband signal ingredient of kurtosis method choice with periodic noise is main frequency
Rate information can not detect the fault type of bearing.
It is specifically described by taking Fig. 7 as an example, from Fig. 7 (a) it can be seen that the band center that spectrum kurtosis method preferably obtains is
5866Hz, bandwidth 1066Hz, which are filtered out by filtering method and individually carries out Envelope Analysis obtain Fig. 7 (b), Fig. 7
(b) compared with figure, apparent failure-frequency information can not be found from spectrogram, only periodic impact noise is distributed in
Entire frequency range.
In conclusion the method for diagnosing faults root of the rolling bearing provided in an embodiment of the present invention based on circulation joint entropy
According to the steady Modeling Theory of bearing vibration signal cycle, the method mapped using kernel function, by data from Euclidean space
It is mapped to Hilbert space, the circulation correlation entropy-spectrum of bearing vibration signal is calculated on this basis, to realize bearing
Fault diagnosis.
Compared with existing spectrum kurtosis method, the method for the embodiment of the present invention can preferably be handled in non-Gaussian noise
Under environment, can under conditions of signal of rolling bearing is interfered by impact noise, accurately to the fault type of rolling bearing into
Row is distinguished, and the requirement of engineering practice can be preferably met.
Those of ordinary skill in the art will appreciate that: attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Process is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention
It can realize by means of software and necessary general hardware platform.Based on this understanding, technical solution of the present invention sheet
The part that contributes to existing technology can be embodied in the form of software products in other words in matter, the computer software
Product can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a calculating
Machine equipment (can be personal computer, server or the network equipment etc.) executes each embodiment of the present invention or embodiment
Certain parts described in method.
All the embodiments in this specification are described in a progressive manner, same and similar between each embodiment
Part may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for dress
Set or system embodiment for, since it is substantially similar to the method embodiment, so describe fairly simple, related place ginseng
See the part explanation of embodiment of the method.Apparatus and system embodiment described above is only schematical, wherein institute
Stating unit as illustrated by the separation member may or may not be physically separated, component shown as a unit
It may or may not be physical unit, it can it is in one place, or may be distributed over multiple network units
On.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.Ability
Domain those of ordinary skill can understand and implement without creative efforts.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited to
This, anyone skilled in the art in the technical scope disclosed by the present invention, the variation that can readily occur in or replaces
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection of claim
Subject to range.
Claims (5)
1. a kind of method for diagnosing faults of the rolling bearing based on circulation joint entropy characterized by comprising
Acquisition rolling bearing is in the bearing data under different faults state respectively, the malfunction include rolling element failure,
Inner ring failure and outer ring failure calculate the fault characteristic frequency of the bearing data under every kind of malfunction；
Windowing process is carried out to the bearing data, bearing data are divided into multiple data blocks, choose gaussian kernel function conduct
The kernel function for recycling joint entropy, calculates the averaging loop joint entropy of each data block, calculates Fu of averaging loop joint entropy
In leaf transformation mean value the domain f Fourier transformation result；
Projection according to the Fourier transformation result in the domain alpha obtains the spectrum distribution of fault-signal as a result, according to described
Event of the fault characteristic frequency of the spectrum distribution result of fault-signal and the bearing data under every kind of malfunction to bearing
Barrier type is judged.
2. the method according to claim 1, wherein the bearing data calculated under every kind of malfunction
Fault characteristic frequency, comprising:
The calculation formula of the characteristic frequency of outer ring failure is as follows:
The calculation formula of the characteristic frequency of inner ring failure is as follows:
The calculation formula of the characteristic frequency of rolling element failure is as follows:
frIndicating the speed of shaft, n indicates the rolling element number of bearing,Indicate that load sagittal plane angle, d indicate to roll
The diameter of body, D indicate bearing bore diameter.
3. according to the method described in claim 2, it is characterized in that, described carry out windowing process, general to the bearing data
Bearing data are divided into multiple data blocks, choose kernel function of the gaussian kernel function as circulation joint entropy, calculate each data
The averaging loop joint entropy of block, comprising:
Bearing data x [n] under different faults state is in the rolling bearing of acquisition and carries out adding window, bearing data x [n] is drawn
It is divided into L data block, each data block has N number of sample point；
Kernel function of the gaussian kernel function as circulation joint entropy is chosen, following for each data block is calculated according to Silverman criterion
The core width cs of ring joint entropy:
X, y indicate the random signal of two equal lengths, and κ (x-y) indicates gaussian kernel function table；
σ indicates the core width of circulation joint entropy；
σ=0.9A*N-1/5 (5)
A indicates the interquartile range of sample standard deviation and sample divided by 1.34 minimum value, and N indicates sample points；
Calculate the averaging loop joint entropy M of each data blockl, l=0,1,2 ..., L-1；
τnIndicate the translation interval between data block；xl[n] indicates the former data of data block, xl[n+τn] indicate that former data translate τn
New data afterwards, κ (xl[n],xl[n+τn]) indicate to calculate the joint entropy for translating former and later two data blocks.
4. according to the method described in claim 3, it is characterized in that, the Fourier for calculating averaging loop joint entropy becomes
Fourier transformation result of the mean value changed in the domain f, comprising:
The centralization for calculating time-domain signal based on L data block recycles joint entropy, and calculates centralization circulation joint entropy in alpha
The Fourier transformation result in domainThe domain alpha refers to modulating frequency, i.e. domain where the failure-frequency of bearing；
N=0,1,2 ..., N-1, l=0,1,2 ..., L-1
α [n] indicates cycle frequency, G (xl[n],xl[n+τn]) indicate that the circulation of two data blocks of translation front and back before centralization is related
Entropy, MlIndicate averaging loop joint entropy, [G (xl[n],xl[n+τn])-MlIndicate that centralization recycles joint entropy；
Calculate the averaging loop joint entropy M of L data blocklFourier transformation mean value
Calculate mean valueFourier transformation result T in the domain fα；
The domain f above refers to carrier frequency, i.e. domain where resonant frequency.
5. according to the method described in claim 4, it is characterized in that, it is described according to the Fourier transformation result in alpha
The projection in domain obtains the spectrum distribution of fault-signal as a result, according to the spectrum distribution result of the fault-signal and every kind of event
The fault characteristic frequency of bearing data under barrier state judges the fault type of bearing, comprising:
The characteristic frequency of rolling element failure is set as 52Hz, the characteristic frequency of inner ring failure is 162Hz, the feature frequency of outer ring failure
Rate is 120Hz；
Projection according to the Fourier transformation result in the domain alpha obtains the spectrum distribution of fault-signal as a result, when failure is believed
Number frequency and rolling element failure characteristic frequency between difference be less than setting threshold value, then judge that the fault type of bearing is
Rolling element failure；When threshold value of the difference between the frequency of fault-signal and the characteristic frequency of inner ring failure less than setting, then sentence
The fault type that off-axis is held is inner ring failure；When the difference between the frequency of fault-signal and the characteristic frequency of outer ring failure is less than
The threshold value of setting then judges the fault type of bearing for outer ring failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811510327.8A CN109668732A (en) | 2018-12-11 | 2018-12-11 | The method for diagnosing faults of rolling bearing based on circulation joint entropy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811510327.8A CN109668732A (en) | 2018-12-11 | 2018-12-11 | The method for diagnosing faults of rolling bearing based on circulation joint entropy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109668732A true CN109668732A (en) | 2019-04-23 |
Family
ID=66143756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811510327.8A Pending CN109668732A (en) | 2018-12-11 | 2018-12-11 | The method for diagnosing faults of rolling bearing based on circulation joint entropy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109668732A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191515A (en) * | 2019-12-05 | 2020-05-22 | 中国电力科学研究院有限公司 | High-precision frequency spectrum identification method and system based on deep learning |
| CN111209713A (en) * | 2020-01-03 | 2020-05-29 | 长江存储科技有限责任公司 | Wafer data processing method and device |
| CN111896256A (en) * | 2020-03-03 | 2020-11-06 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Bearing fault diagnosis method based on deep nuclear processing |
| CN116383721A (en) * | 2023-05-25 | 2023-07-04 | 华北电力大学 | Rotation equipment detection method based on cyclic correlation entropy spectrum |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302940A (en) * | 2015-09-16 | 2016-02-03 | 大连理工大学 | Carrier frequency estimation method based on circular correlation entropy |
| CN105933259A (en) * | 2016-04-21 | 2016-09-07 | 大连理工大学 | Carrier frequency estimation method based on cyclic correlation entropy spectrum of compressive sensing reconstruction |
| CN105938468A (en) * | 2016-06-07 | 2016-09-14 | 北京交通大学 | Fault diagnosis method for rolling bearing |
-
2018
- 2018-12-11 CN CN201811510327.8A patent/CN109668732A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302940A (en) * | 2015-09-16 | 2016-02-03 | 大连理工大学 | Carrier frequency estimation method based on circular correlation entropy |
| CN105933259A (en) * | 2016-04-21 | 2016-09-07 | 大连理工大学 | Carrier frequency estimation method based on cyclic correlation entropy spectrum of compressive sensing reconstruction |
| CN105938468A (en) * | 2016-06-07 | 2016-09-14 | 北京交通大学 | Fault diagnosis method for rolling bearing |
Non-Patent Citations (1)
| Title |
|---|
| 付云骁等: ""基于乘积函数相关熵的滚动轴承故障辨识方法"", 《应用基础与工程科学学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191515A (en) * | 2019-12-05 | 2020-05-22 | 中国电力科学研究院有限公司 | High-precision frequency spectrum identification method and system based on deep learning |
| CN111209713A (en) * | 2020-01-03 | 2020-05-29 | 长江存储科技有限责任公司 | Wafer data processing method and device |
| CN111209713B (en) * | 2020-01-03 | 2023-08-18 | 长江存储科技有限责任公司 | Wafer data processing method and device |
| CN111896256A (en) * | 2020-03-03 | 2020-11-06 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Bearing fault diagnosis method based on deep nuclear processing |
| CN116383721A (en) * | 2023-05-25 | 2023-07-04 | 华北电力大学 | Rotation equipment detection method based on cyclic correlation entropy spectrum |
| CN116383721B (en) * | 2023-05-25 | 2023-12-12 | 华北电力大学 | Rotation equipment detection method based on cyclic correlation entropy spectrum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109668732A (en) | The method for diagnosing faults of rolling bearing based on circulation joint entropy | |
| Wang et al. | Enhanced generative adversarial network for extremely imbalanced fault diagnosis of rotating machine | |
| CN106408088B (en) | A kind of rotating machinery method for diagnosing faults based on deep learning theory | |
| Liu et al. | TScatNet: An interpretable cross-domain intelligent diagnosis model with antinoise and few-shot learning capability | |
| Yan et al. | Fault diagnosis of rotating machinery equipped with multiple sensors using space-time fragments | |
| Pinheiro et al. | Vibration analysis in turbomachines using machine learning techniques | |
| CN109858104A (en) | A kind of rolling bearing health evaluating and method for diagnosing faults and monitoring system | |
| CN109813547A (en) | Rotating machinery local type method for diagnosing faults based on sparse decomposition optimization algorithm | |
| CN108573193A (en) | A kind of rolling bearing multiple faults coupling mechanism and fault features extracting method | |
| Zhang et al. | Sparsity-aware tight frame learning with adaptive subspace recognition for multiple fault diagnosis | |
| CN112633098A (en) | Fault diagnosis method and system for rotary machine and storage medium | |
| CN107559228B (en) | Method based on bispectral data detection and diagnosis fan trouble | |
| Liu et al. | An intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits | |
| Shukla et al. | Power quality disturbances classification based on Gramian angular summation field method and convolutional neural networks | |
| CN109270836A (en) | A kind of integrated signal extracting method, device and equipment | |
| Li et al. | Data augmentation via variational mode reconstruction and its application in few-shot fault diagnosis of rolling bearings | |
| Wang et al. | Robust bearing degradation assessment method based on improved CVA | |
| CN117827784A (en) | Noise log filtering method and system | |
| Sun et al. | Intelligent fault warning method of rotating machinery with intraclass and interclass infographic embedding | |
| Zhong et al. | Fault diagnosis of motor bearing using self-organizing maps | |
| Jiao et al. | An Improved Dual‐Kurtogram‐Based T2 Control Chart for Condition Monitoring and Compound Fault Diagnosis of Rolling Bearings | |
| Wen et al. | A novel SE-weighted multi-scale Hedging CNN approach for fault diagnosis of wind turbine | |
| Lee et al. | Generative adversarial network-based signal inpainting for automatic modulation classification | |
| Zhang et al. | A new modelling and feature extraction method based on complex network and its application in machine fault diagnosis | |
| Chen et al. | An interpretable health indicator for bearing condition monitoring based on semi-supervised autoencoder latent space variance maximization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190423 |
|
| WD01 | Invention patent application deemed withdrawn after publication |